CN107065567A - A kind of automatic stopping control system that control is constrained based on adaptive neural network - Google Patents
A kind of automatic stopping control system that control is constrained based on adaptive neural network Download PDFInfo
- Publication number
- CN107065567A CN107065567A CN201710363924.1A CN201710363924A CN107065567A CN 107065567 A CN107065567 A CN 107065567A CN 201710363924 A CN201710363924 A CN 201710363924A CN 107065567 A CN107065567 A CN 107065567A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- mfrac
- mover
- alpha
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Medicines Containing Antibodies Or Antigens For Use As Internal Diagnostic Agents (AREA)
Abstract
The invention discloses a kind of automatic stopping control system that control is constrained based on adaptive neural network, belong to intelligent automobile technical field, the present invention includes the path planning based on ultrasonic sensor, the PID controller based on RBF neural, dynamic constrained limitation, Full Vehicle Dynamics model, the observer based on RBF neural and anti-saturation compensator.Using said structure, it is contemplated that input constraint restrictive condition, whole system has complete control thinking.In the case where meeting reality, verified through simulation example, the present invention has good tracking performance, robustness and adaptability.
Description
Technical field
The present invention relates to a kind of automatic stopping control system that control is constrained based on adaptive neural network, belong to intelligent vapour
Car technical field.
Background technology
For many drivers, in urban compact region, parking is a kind of painful experience.Big city parking space
Limited, automobile is driven into narrow space turns into a required skill.Few situations for having stopped car without taking some twists and turns,
Parking may smoothly not cause traffic jam, driver's neurolysis, or occur situations such as cause vehicle bumper to be hit curved.From
Dynamic stopping technical can effectively solve the problem that above mentioned problem, makes automotive safety and rapidly stops to designated area.
Automatic stopping technology is in progressively ripe process.The automatic parking system of prior art, due to wheel turning angle
Saturation problem and cause it is similar can not tracking fixed valure the problem of, this causes unnecessary trouble to quick parking.
The content of the invention
The present invention first purpose be to provide a kind of automatic stop process, methods described using wheel turning angle as object,
Anti-saturation compensator, RBF observers, PID controller, dynamic constrained module are controlled to the parking path of vehicle；The RBF
Observer is to PID controller and anti-saturation compensator input signal, it is ensured that the two normal work；The PID controller controls car
The actual value of wheel steering angle is consistent with predetermined value, and angle control of the anti-saturation compensator to PID controller is repaiied
Just, the dynamic constrained module enters row constraint to the angle and rate of change of wheel steering.
In one embodiment of the invention, the PID controller is based on RBF neural, and it is described as：
Wherein netjRepresent the output of the first layer of RBF neural, oijRepresent that input layer is input to jth i-th
The weighted value of individual intermediate node, xcj(k) it is three inputs, e (k)-e (k-1), e (k), e (k) -2e (k-1)+e (k- is corresponded to respectively
2), wherein e (k) is φ*(k)-φ (k-1)-ε (k), φ*(k), the Vehicular turn angle needed for φ (k) expressions system and reality
Steering angle, ε (k) represents thermal compensation signal, α0(k) it is the Vehicular turn angle at the k moment without constraint, α (k) is after constrained
The Vehicular turn angle at k moment, KjCorrespondence Kp, Ki, KdParameter, ηbFor parameter learning speed.
In one embodiment of the invention, the anti-saturation compensator is described as：
Wherein, ε (k) is the anti-saturation compensator signal at k moment, and μ is the positive number less than 1, and α (k-1) is the k-1 moment
Vehicular turn angle, α0(k) it is the Vehicular turn angle at the k moment without constraint,Obtained by RBF neural
Jacobian information.
In one embodiment of the invention, the constraints of the dynamic constrained module is：
Wherein, TsThe systematic sampling time is represented,The minimum and maximum rate of change at Vehicular turn angle is represented respectively,
αmin, αmaxThe minimum and maximum value at Vehicular turn angle is represented respectively.
In one embodiment of the invention, in the dynamic constrained condition, the excursion of body corner for -45~
45 °, vehicle body angular rate of change scope is -20~20 °/s.
In one embodiment of the invention, the kinetic model of the vehicle is：
Wherein, u represents speed, LwRepresent vehicle antero posterior axis wheelbase.
In one embodiment of the invention, the RBF observers are described as follows：
Make X=[x1,x2,…xn]TFor the input vector of neutral net, G=[g1,g2,…,gj,…gm]TFor RBF nerve nets
The radial direction base vector of network, gjStructure be：
Wherein Fj=[fj1,fj2,…,fji,…fjn]T, i=1,2 ... n represent node j center vector.Dj=[d1,
d2,…,dm]TFor the sound stage width vector of neutral net, djThe sound stage width parameter of j nodes is represented, is positive number.Define the power of neutral net
Weight vector is S=[s1,s2,…,sj…,sm]T, it is identified network and is output as：
Specifically iterative algorithm is：
dj(k)=dj(k-1)+ηΔdj(k)+κ(dj(k-1)-dj(k-2))
fji(k)=fji(k-1)+ηΔfji(k)+κ(fji(k-1)-fji(k-2))
The recognizer of Jacobian information is：
Second object of the present invention is to provide a kind of automatic stopping control system, contains PID controller, dynamic constrained mould
Block, anti-saturation compensator, RBF observers and ultrasonic sensor, by wiredly and/or wirelessly connecting；The supersonic sensing
Device is arranged on vehicle, and wheel steering angle signal is transmitted to PID controller；It is defeated that the dynamic constrained module receives PID controller
The wheel steering angle signal gone out, and the amplitude and rate of change that are turned to it enter row constraint, and the steering angle signal after constraint is inputted
To anti-saturation compensator；The RBF observers transmit Jacobian information to anti-saturation compensator and PID controller respectively；
In one embodiment of the invention, the PID controller based on RBF neural, the PID control
Device is based on RBF neural, and it is described as：
Wherein netjRepresent the output of the first layer of RBF neural, oijRepresent that input layer is input to jth i-th
The weighted value of individual intermediate node, xcj(k) it is three inputs, e (k)-e (k-1), e (k), e (k) -2e (k-1)+e (k- is corresponded to respectively
2), wherein e (k) is φ*(k)-φ (k-1)-ε (k), φ*(k), the Vehicular turn angle needed for φ (k) expressions system and reality
Steering angle, ε (k) represents thermal compensation signal, α0(k) it is the Vehicular turn angle at the k moment without constraint, α (k) is after constrained
The Vehicular turn angle at k moment, KjCorrespondence Kp, Ki, KdParameter, ηbFor parameter learning speed.
In one embodiment of the invention, described dynamic constrained module is output as the Vehicular turn after constraint
Angle, the amplitude turned to for limiting wheel and rate of change, it is ensured that vehicle meets actual Vehicular turn feelings in Turning travel
Condition, it is ensured that safety, in one embodiment of the invention, the constraints of the dynamic constrained module is：
Wherein, TsThe systematic sampling time is represented,The minimum and maximum rate of change at Vehicular turn angle is represented respectively,
αmin, αmaxThe minimum and maximum value at Vehicular turn angle is represented respectively.
In one embodiment of the invention, the excursion of the body corner is -45~45 °, vehicle body angular rate of change
Scope is -20~20 °/s.
In one embodiment of the invention, described anti-saturation compensator, it is output as dynamic thermal compensation signal, uses
With compensate because dynamic constrained module exist and caused by output do not follow or follow excessively slow situation.
In one embodiment of the invention, the vehicle is output as the body corner of vehicle, its act on be to based on
The observer of RBF neural, Jacobian information necessary to obtain system.
In one embodiment of the invention, the Jacobian information is automobile body angle for wheel turning angle
Partial derivative.
Third object of the present invention is to provide the vehicle using the automatic stop process.
The present invention also provides application of the automatic stop process in intelligent automobile field.
Beneficial effect：A kind of automatic stopping for constraining control based on adaptive neural network proposed by the present invention controls system
System, realizes the estimation of Jacobian information first with the observer technology based on RBF neural, base is devised based on this
In the PID controller of RBF neural, input constraint condition is with the addition of on the basis of this controller, and add anti-full
Saturated phenomenon produced problem is tackled with compensator, whole control system is more conformed to actual conditions, enhances system
Reliability.Reduce client and find parking stall and the trouble stopped, improve the utilization rate of time.
Brief description of the drawings
Fig. 1 is automatic stopping Control System Design block diagram proposed by the invention；
Fig. 2 is automatic parking path planning schematic diagram of the invention；
Fig. 3 is the given figure in path under one embodiment of the present invention；
Fig. 4 is the pid parameter estimate schematic diagram under one embodiment of the present invention；
Fig. 5 is the RBF observer weights estimation value schematic diagrames under one embodiment of the present invention；
Fig. 6 is the Jacobian information under one embodiment of the present invention and the estimate schematic diagram of compensator signal；
Fig. 7 is the output response comparison schematic diagram of the invention under two kinds of embodiments；PIDNN is controlled for the PID of the present invention
Output under device control processed；PID is the output under traditional PID controller control；
Fig. 8 is the PID controller that steering angle comparison schematic diagram PIDNN of the present invention under two kinds of embodiments is the present invention
Output under control；PID is the output under traditional PID controller control.
Embodiment
Embodiment 1
The a kind of of the present invention constrains the automatic stopping control system of control with Vehicular turn angle based on adaptive neural network
For object, the angle control method of the PID controller based on RBF neural is modified with reference to anti-saturation compensator, if
Count block diagram as shown in Figure 1.
The automatic stopping control system mainly includes：Path planning module, it is the PID controller based on RBF neural, dynamic
Modal constraint module, anti-saturation compensator, Full Vehicle Dynamics model and the observer based on RBF neural.RBF observers are exported
Jacobian information is to PID controller and anti-saturation compensator；The PID controller calculates the reality for obtaining wheel turning angle
Value, the input of the anti-saturation compensator is the difference of the wheel turning angle through affined wheel turning angle and without constraint, is led to
The processing of anti-saturation compensator is crossed, the angle that PID controller is exported is modified；The dynamic constrained module is to wheel steering
Angle and the wheel turning angle that enters after row constraint, and output constraint of rate of change, then the signal is transferred to vehicle, obtains actual
Body corner.
Operated as follows by the method for emulation experiment：
Step one：Utilize ultrasonic sensor mensuration distance：
As shown in Fig. 2 wherein LvFor motor vehicle length, LwFor front and rear shaft length, WvFor vehicle width, LsFor length of parking, Δ
D is the safe distance between two cars, and d is the distance of vehicle body center line and roadside-vehicle.Vehicle forward is detected by ultrasonic sensor
To when having parking stall, vehicle has reached Q3At position, the parking path of vehicle is divided into four sections, 1) vehicle with form of straight lines after
Move back process (i.e. Fig. 2 cathetus section Q3Q2Part)；2) vehicle right turn process (i.e. curved section Q in Fig. 22Q1Part)；3) vehicle is returned
It is 0 to be diverted to steering angle, straight line fallback procedures (i.e. Fig. 2 cathetus section Q1Q0Part)；4) vehicle turns left to draw back to automobile body
Angle for 0 process (i.e. curved section Q in Fig. 20O parts).
Step 2, the design of the PID controller based on RBF neural.
Shown in typical PID controller design such as formula (1)：
α0(k)=α (k-1)+kp(e(k)-e(k-1))+kie(k)+kd(e(k)-2e(k-1)+e(k-2)) (1)
Wherein α (k-1) is the Vehicular turn angle at k-1 moment, α0(k) it is the Vehicular turn angle at the k moment without constraint, e
(k) it is φ*(k)-φ (k-1)-ε (k), is systematic error, φ*(k), the Vehicular turn angle needed for φ (k) expressions system and reality
Steering angle, ε (k) represent thermal compensation signal, kp, ki, kdRespectively PID gain.
For the PID controller based on RBF neural, three intermediate nodes are defined, and define neutral net the
Shown in one layer of output such as formula (2)：
Wherein oijRepresent that input layer is input to the weighted value of j-th of intermediate node for i-th, it is carried out more by rule of iteration
Replace, the o in this simulation exampleijInitial value be：
xcj(k) be three inputs, corresponded to respectively in this simulation example e (k)-e (k-1), e (k) and e (k) -2e (k-1)+
e(k-2).Shown in the output such as formula (3) for defining PID controller：
KjCorrespondence Kp, Ki, KdParameter, it is also to be substituted by rule of iteration, and initial value is set in this simulation example
[25,0.7,0.3]T, y (netj) be defined as：
Therefore the derivative of above formula can be obtained is：
KjAnd o (k+1)ij(k+1) rule of iteration is as follows：
Wherein ηbFor parameter learning speed, it is set in this simulation example [- 0.1, -0.08, -0.15]T。oijInitial value
For：
Step 3, sets up dynamic constrained condition, to obtain meeting actual Vehicular turn angle.
Dynamic constrained condition can be described as：
Wherein, TsThe systematic sampling time is represented, 0.02s is set in this simulation example, Sat () function is defined as：
Step 4, Full Vehicle Dynamics model is set up to obtain body corner.
Auto model can be described as：
Wherein u represents speed, LwRepresent vehicle antero posterior axis wheelbase.
Step 5, the design of the observer based on RBF neural
Make X=[x1,x2,…xn]TFor the input vector of neutral net, the radial direction base vector for choosing RBF neural is G
=[g1,g2,…,gj,…gm]T, wherein gjFor Gaussian function, its structure is：
Wherein Fj=[fj1,fj2,…,fji,…fjn]T, i=1,2 ... n represent node j center vector.It is real in emulation
F in examplejInitial value be
The sound stage width vector for defining neutral net is Dj=[d1,d2,…,dm]T, djThe sound stage width parameter of j nodes is represented, is just
Number, the d in this simulation examplej(0) initial value is dj(0)=[7.15 7.15 7.15 7.15 7.15 7.15]T.Definition nerve
The weight vectors of network are S=[s1,s2,…,sj…,sm]T, S (0) initial value is S (0)=[0.01 in this simulation example
0.01 0.01 0.01 0.01 0.01]T, can then be identified network and be output as：
And the iterative algorithm for exporting weight vectors, node base fat vector and intermediate node base vector can be by gradient descent method
To obtain, specific iterative algorithm is as follows：
dj(k)=dj(k-1)+ηΔdj(k)+κ(dj(k-1)-dj(k-2)) (14)
fji(k)=fji(k-1)+ηΔfji(k)+κ(fji(k-1)-fji(k-2)) (16)
By (10) formula and (11) formula, the recognizer that can obtain control system Jacobian information is：
Step 6, the design of anti-saturation compensator, the anti-saturation compensator of design is described as：
Wherein, ε (k) is the compensator signal at k moment, and μ is the positive number less than 1,It is to be obtained by observer
Jacobian information.
Automatic stopping is carried out using unmodified PID controller, as Figure 7-8, solid line is this to the response diagram of vehicle
The emulation aircraft pursuit course that the method for invention is obtained, dotted line is the emulation obtained using existing unmodified PID controller
Aircraft pursuit course, through being compared with unmodified PID controller, find automatic stopping control system proposed by the invention with
Track faster, shows better performance.Simulation result shows that proposed method is effective.
Although the present invention is disclosed as above with preferred embodiment, it is not limited to the present invention, any to be familiar with this skill
The people of art, without departing from the spirit and scope of the present invention, can do various changes and modification, therefore the protection model of the present invention
Enclose being defined of being defined by claims.
Claims (10)
1. a kind of automatic stop process, it is characterised in that methods described is compensated using wheel turning angle as object by anti-saturation
Device, RBF observers, PID controller, dynamic constrained module are controlled to the parking path of vehicle；The RBF observers to
PID controller and anti-saturation compensator input Jacobian information；The PID controller calculates the reality for obtaining wheel turning angle
Value, the anti-saturation compensator is modified to the angle of PID controller, angle of the dynamic constrained module to wheel steering
The wheel turning angle entered with rate of change after row constraint, and output constraint.
2. according to the method described in claim 1, it is characterised in that the PID controller is based on RBF neural, it is described
For：
<mrow>
<msub>
<mi>net</mi>
<mi>j</mi>
</msub>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>3</mn>
</munderover>
<msub>
<mi>o</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<mo>&CenterDot;</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>c</mi>
<mi>j</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msub>
<mi>&alpha;</mi>
<mn>0</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>&alpha;</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>+</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>3</mn>
</munderover>
<msub>
<mi>K</mi>
<mi>j</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>&CenterDot;</mo>
<mi>y</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>net</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mi>y</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>net</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mrow>
<mn>1</mn>
<mo>-</mo>
<msup>
<mi>exp</mi>
<mrow>
<mo>-</mo>
<msub>
<mi>net</mi>
<mi>j</mi>
</msub>
</mrow>
</msup>
</mrow>
<mrow>
<mn>1</mn>
<mo>+</mo>
<msup>
<mi>exp</mi>
<mrow>
<mo>-</mo>
<msub>
<mi>net</mi>
<mi>j</mi>
</msub>
</mrow>
</msup>
</mrow>
</mfrac>
</mrow>
<mrow>
<msup>
<mi>y</mi>
<mo>&prime;</mo>
</msup>
<mrow>
<mo>(</mo>
<msub>
<mi>net</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mn>2</mn>
</mfrac>
<msup>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>-</mo>
<mi>y</mi>
<mo>(</mo>
<mrow>
<msub>
<mi>net</mi>
<mi>j</mi>
</msub>
</mrow>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
<mrow>
<msub>
<mi>K</mi>
<mi>j</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msub>
<mi>K</mi>
<mi>j</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<msub>
<mi>&eta;</mi>
<mi>b</mi>
</msub>
<mi>e</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mfrac>
<mrow>
<mo>&part;</mo>
<mover>
<mi>&phi;</mi>
<mo>^</mo>
</mover>
</mrow>
<mrow>
<mo>&part;</mo>
<mi>&alpha;</mi>
</mrow>
</mfrac>
<mi>y</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>net</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msub>
<mi>o</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msub>
<mi>o</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<msub>
<mi>&eta;</mi>
<mi>b</mi>
</msub>
<mi>e</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mfrac>
<mrow>
<mo>&part;</mo>
<mover>
<mi>&phi;</mi>
<mo>^</mo>
</mover>
</mrow>
<mrow>
<mo>&part;</mo>
<mi>&alpha;</mi>
</mrow>
</mfrac>
<msub>
<mi>K</mi>
<mi>j</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<msup>
<mi>y</mi>
<mo>&prime;</mo>
</msup>
<mrow>
<mo>(</mo>
<msub>
<mi>net</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
<msub>
<mi>x</mi>
<mrow>
<mi>c</mi>
<mi>j</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</mrow>
Wherein netjRepresent the output of the first layer of RBF neural, oijRepresent that input layer is input in j-th for i-th
The weighted value of intermediate node, xcj(k) it is three inputs, e (k)-e (k-1), e (k), e (k) -2e (k-1)+e (k-2) is corresponded to respectively,
Wherein e (k) is φ*(k)-φ (k-1)-ε (k), φ*(k), the Vehicular turn angle needed for φ (k) expressions system and actual steering
Angle, ε (k) represents thermal compensation signal, α0(k) it is the Vehicular turn angle at the k moment without constraint, when α (k) is the k after constrained
The Vehicular turn angle at quarter, KjCorrespondence Kp, Ki, KdParameter, ηbFor parameter learning speed.
3. according to the method described in claim 1, it is characterised in that the anti-saturation compensator is described as：
<mrow>
<mi>&epsiv;</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>&mu;</mi>
<mi>&epsiv;</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mfrac>
<mrow>
<mo>&part;</mo>
<mover>
<mi>&phi;</mi>
<mo>^</mo>
</mover>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mo>&part;</mo>
<mi>&alpha;</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mrow>
<mo>(</mo>
<msub>
<mi>&alpha;</mi>
<mn>0</mn>
</msub>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
<mo>-</mo>
<mi>&alpha;</mi>
<mo>(</mo>
<mrow>
<mi>k</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mo>)</mo>
<mo>)</mo>
</mrow>
</mrow>
Wherein, ε (k) is the anti-saturation compensator signal at k moment, and μ is the positive number less than 1, and α (k-1) is the vehicle at k-1 moment
Steering angle, α0(k) it is the Vehicular turn angle at the k moment without constraint,For the Jacobian obtained by RBF neural
Information.
4. according to the method described in claim 1, it is characterised in that the constraints of the dynamic constrained module is：
<mrow>
<mi>&alpha;</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>S</mi>
<mi>a</mi>
<mi>t</mi>
<mrow>
<mo>{</mo>
<mrow>
<mrow>
<mo>(</mo>
<mrow>
<mi>&alpha;</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>k</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mi>S</mi>
<mi>a</mi>
<mi>t</mi>
<mrow>
<mo>{</mo>
<mrow>
<mrow>
<mo>(</mo>
<mrow>
<msub>
<mi>&alpha;</mi>
<mn>0</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mi>&alpha;</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>k</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
<mo>)</mo>
</mrow>
<mo>,</mo>
<mover>
<mrow>
<msub>
<mi>T</mi>
<mi>s</mi>
</msub>
<msub>
<mi>&alpha;</mi>
<mi>min</mi>
</msub>
</mrow>
<mo>&CenterDot;</mo>
</mover>
<mo>,</mo>
<mover>
<mrow>
<msub>
<mi>T</mi>
<mi>s</mi>
</msub>
<msub>
<mi>&alpha;</mi>
<mi>max</mi>
</msub>
</mrow>
<mo>&CenterDot;</mo>
</mover>
</mrow>
<mo>}</mo>
</mrow>
</mrow>
<mo>)</mo>
</mrow>
<mo>,</mo>
<msub>
<mi>&alpha;</mi>
<mi>min</mi>
</msub>
<mo>,</mo>
<msub>
<mi>&alpha;</mi>
<mi>max</mi>
</msub>
</mrow>
<mo>}</mo>
</mrow>
</mrow>
<mrow>
<mi>S</mi>
<mi>a</mi>
<mi>t</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>a</mi>
<mo>,</mo>
<mi>b</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mi>a</mi>
<mo>(</mo>
<mi>x</mi>
<mo>&le;</mo>
<mi>a</mi>
<mo>)</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mi>x</mi>
<mo>(</mo>
<mi>a</mi>
<mo><</mo>
<mi>x</mi>
<mo><</mo>
<mi>b</mi>
<mo>)</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mi>b</mi>
<mo>(</mo>
<mi>x</mi>
<mo>&GreaterEqual;</mo>
<mi>b</mi>
<mo>)</mo>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
Wherein, TsThe systematic sampling time is represented,The minimum and maximum rate of change at Vehicular turn angle, α are represented respectivelymin,
αmaxThe minimum and maximum value at Vehicular turn angle is represented respectively；A, b represent minimum value and maximum respectively.
5. method according to claim 4, it is characterised in that in the dynamic constrained condition, the excursion of body corner
For -45~45 °, vehicle body angular rate of change scope is -20~20 °/s.
6. according to the method described in claim 1, it is characterised in that the kinetic model of the vehicle is：
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>x</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>x</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<msub>
<mi>T</mi>
<mi>s</mi>
</msub>
<mi>u</mi>
<mi> </mi>
<mi>cos</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>&phi;</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>y</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>y</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<msub>
<mi>T</mi>
<mi>s</mi>
</msub>
<mi>u</mi>
<mi> </mi>
<mi>sin</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>&phi;</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>&phi;</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>k</mi>
<mo>+</mo>
<mn>1</mn>
</mrow>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>&phi;</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<msub>
<mi>T</mi>
<mi>s</mi>
</msub>
<mi>u</mi>
<mi> </mi>
<mi>tan</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>&phi;</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</mrow>
<mo>)</mo>
</mrow>
<mo>/</mo>
<msub>
<mi>L</mi>
<mi>w</mi>
</msub>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
Wherein, u represents speed, LwRepresent vehicle antero posterior axis wheelbase.
7. according to the method described in claim 1, it is characterised in that the RBF observers are described as follows：
Make X=[x1,x2,…xn]TFor the input vector of neutral net, G=[g1,g2,…,gj,…gm]TFor RBF neural
Radial direction base vector, gjStructure be：
<mrow>
<msub>
<mi>g</mi>
<mi>j</mi>
</msub>
<mo>=</mo>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<mo>-</mo>
<mfrac>
<mrow>
<mo>|</mo>
<mo>|</mo>
<mi>X</mi>
<mo>-</mo>
<msub>
<mi>F</mi>
<mi>j</mi>
</msub>
<mo>|</mo>
<msup>
<mo>|</mo>
<mn>2</mn>
</msup>
</mrow>
<mrow>
<mn>2</mn>
<msubsup>
<mi>d</mi>
<mi>j</mi>
<mn>2</mn>
</msubsup>
</mrow>
</mfrac>
<mo>)</mo>
</mrow>
<mo>,</mo>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
<mo>,</mo>
<mn>2</mn>
<mo>,</mo>
<mo>...</mo>
<mi>m</mi>
</mrow>
Wherein Fj=[fj1,fj2,…,fji,…fjn]T, i=1,2 ... n represent node j center vector；Dj=[d1,d2,…,
dm]TFor the sound stage width vector of neutral net, djThe sound stage width parameter of j nodes is represented, is positive number；Define the weight vectors of neutral net
For S=[s1,s2,…,sj…,sm]T, it is identified network and is output as：
Specifically iterative algorithm is：
<mrow>
<msub>
<mi>s</mi>
<mi>j</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msub>
<mi>s</mi>
<mi>j</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mi>&eta;</mi>
<mrow>
<mo>(</mo>
<mi>&phi;</mi>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
<mo>-</mo>
<mover>
<mi>&phi;</mi>
<mo>^</mo>
</mover>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
<mo>)</mo>
</mrow>
<msub>
<mi>g</mi>
<mi>j</mi>
</msub>
<mo>+</mo>
<mi>&kappa;</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>s</mi>
<mi>j</mi>
</msub>
<mo>(</mo>
<mrow>
<mi>k</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mo>)</mo>
<mo>-</mo>
<msub>
<mi>s</mi>
<mi>j</mi>
</msub>
<mo>(</mo>
<mrow>
<mi>k</mi>
<mo>-</mo>
<mn>2</mn>
</mrow>
<mo>)</mo>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msub>
<mi>&Delta;d</mi>
<mi>j</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>&eta;</mi>
<mrow>
<mo>(</mo>
<mi>&phi;</mi>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
<mo>-</mo>
<mover>
<mi>&phi;</mi>
<mo>^</mo>
</mover>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
<mo>)</mo>
</mrow>
<msub>
<mi>s</mi>
<mi>j</mi>
</msub>
<msub>
<mi>g</mi>
<mi>j</mi>
</msub>
<mfrac>
<mrow>
<mo>|</mo>
<mo>|</mo>
<mi>X</mi>
<mo>-</mo>
<msub>
<mi>F</mi>
<mi>j</mi>
</msub>
<mo>|</mo>
<msup>
<mo>|</mo>
<mn>2</mn>
</msup>
</mrow>
<msubsup>
<mi>d</mi>
<mi>j</mi>
<mn>3</mn>
</msubsup>
</mfrac>
</mrow>
dj(k)=dj(k-1)+ηΔdj(k)+κ(dj(k-1)-dj(k-2))
<mrow>
<msub>
<mi>&Delta;f</mi>
<mrow>
<mi>j</mi>
<mi>i</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>&eta;</mi>
<mrow>
<mo>(</mo>
<mi>&phi;</mi>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
<mo>-</mo>
<mover>
<mi>&phi;</mi>
<mo>^</mo>
</mover>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
<mo>)</mo>
</mrow>
<msub>
<mi>s</mi>
<mi>j</mi>
</msub>
<mfrac>
<mrow>
<msub>
<mi>x</mi>
<mi>j</mi>
</msub>
<mo>-</mo>
<msub>
<mi>f</mi>
<mrow>
<mi>j</mi>
<mi>i</mi>
</mrow>
</msub>
</mrow>
<msubsup>
<mi>d</mi>
<mi>j</mi>
<mn>2</mn>
</msubsup>
</mfrac>
</mrow>
fji(k)=fji(k-1)+ηΔfji(k)+κ(fji(k-1)-fji(k-2))
The recognizer of Jacobian information is：
<mrow>
<mfrac>
<mrow>
<mo>&part;</mo>
<mi>&phi;</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mo>&part;</mo>
<mi>&alpha;</mi>
</mrow>
</mfrac>
<mo>=</mo>
<mfrac>
<mrow>
<mo>&part;</mo>
<mover>
<mi>&phi;</mi>
<mo>^</mo>
</mover>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mo>&part;</mo>
<mi>&alpha;</mi>
</mrow>
</mfrac>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>m</mi>
</munderover>
<msub>
<mi>s</mi>
<mi>j</mi>
</msub>
<msub>
<mi>g</mi>
<mi>j</mi>
</msub>
<mfrac>
<mrow>
<msub>
<mi>f</mi>
<mrow>
<mi>j</mi>
<mi>i</mi>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
</mrow>
<msubsup>
<mi>d</mi>
<mi>j</mi>
<mn>2</mn>
</msubsup>
</mfrac>
<mo>.</mo>
</mrow>
8. one kind application any methods describeds of claim 1-7 realize self-stopping automatic stopping control system, its feature exists
In containing PID controller, dynamic constrained module, anti-saturation compensator, RBF observers and ultrasonic sensor, by wired
And/or wireless connection；The ultrasonic sensor is arranged on vehicle, and wheel steering angle signal is transmitted to PID controller；It is described
Dynamic constrained module receives the wheel steering angle signal of PID controller output, and the amplitude and rate of change turned to it is carried out about
Beam, the steering angle signal after constraint is inputted to anti-saturation compensator；The RBF observers respectively to anti-saturation compensator and
PID controller transmits Jacobian information.
9. the vehicle of the application any methods describeds of claim 1-7.
10. any methods describeds of claim 1-7 are in the application of intelligent automobile field.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710363924.1A CN107065567A (en) | 2017-05-22 | 2017-05-22 | A kind of automatic stopping control system that control is constrained based on adaptive neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710363924.1A CN107065567A (en) | 2017-05-22 | 2017-05-22 | A kind of automatic stopping control system that control is constrained based on adaptive neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107065567A true CN107065567A (en) | 2017-08-18 |
Family
ID=59611037
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710363924.1A Pending CN107065567A (en) | 2017-05-22 | 2017-05-22 | A kind of automatic stopping control system that control is constrained based on adaptive neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107065567A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107697065A (en) * | 2017-10-16 | 2018-02-16 | 北方工业大学 | Automatic parking control method for general parking scene |
| CN108197704A (en) * | 2017-12-29 | 2018-06-22 | 贵州航天南海科技有限责任公司 | A kind of stereo garage control method |
| CN109086492A (en) * | 2018-07-11 | 2018-12-25 | 大连理工大学 | A kind of wire frame representation of body structure threedimensional model and deformation method and system |
| CN109188912A (en) * | 2018-10-12 | 2019-01-11 | 国网浙江省电力有限公司绍兴供电公司 | A kind of control method for energy storage device in grid-connected distributed energy resource system |
| CN109921924A (en) * | 2019-02-14 | 2019-06-21 | 电子科技大学 | A kind of intelligent automobile multilayer stereoscopic joint control system modeling method |
| CN110310500A (en) * | 2019-06-19 | 2019-10-08 | 中汽研（天津）汽车工程研究院有限公司 | A kind of autonomous valet parking system and method based on GRNN network |
| US20220204018A1 (en) * | 2020-12-29 | 2022-06-30 | GM Global Technology Operations LLC | Vehicle control using neural network controller in combination with model-based controller |
| CN114701875A (en) * | 2022-03-08 | 2022-07-05 | 中国人民解放军空军工程大学 | Guiding device and method for loading and unloading of railway vehicle under light condition |
| US11613249B2 (en) | 2018-04-03 | 2023-03-28 | Ford Global Technologies, Llc | Automatic navigation using deep reinforcement learning |
| CN116461499A (en) * | 2023-03-02 | 2023-07-21 | 合众新能源汽车股份有限公司 | Parking control method and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105818712A (en) * | 2016-03-17 | 2016-08-03 | 电子科技大学 | Self-adaptive starting control method for four-wheel hub electric automobile |
| CN206797381U (en) * | 2017-05-22 | 2017-12-26 | 江南大学 | A kind of automatic stopping control system and automobile |
-
2017
- 2017-05-22 CN CN201710363924.1A patent/CN107065567A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105818712A (en) * | 2016-03-17 | 2016-08-03 | 电子科技大学 | Self-adaptive starting control method for four-wheel hub electric automobile |
| CN206797381U (en) * | 2017-05-22 | 2017-12-26 | 江南大学 | A kind of automatic stopping control system and automobile |
Non-Patent Citations (3)
| Title |
|---|
| JING DENG 等: "Adaptive neural network automatic parking constrained control via anti-windup compensator", 《ADVANCES IN MECHANICAL ENGINEERING》 * |
| WENXU YAN 等: "Data-driven automatic parking constrained control for four-wheeled mobile vehicles", 《INTERNATIONAL JOURNAL OF ADVANCED ROBOTICS SYSTEMS》 * |
| 王健 等: "基于线性扩张状态观测器的平行泊车路径跟踪", 《华南理工大学学报（自然科学版）》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107697065A (en) * | 2017-10-16 | 2018-02-16 | 北方工业大学 | Automatic parking control method for general parking scene |
| CN108197704A (en) * | 2017-12-29 | 2018-06-22 | 贵州航天南海科技有限责任公司 | A kind of stereo garage control method |
| US11613249B2 (en) | 2018-04-03 | 2023-03-28 | Ford Global Technologies, Llc | Automatic navigation using deep reinforcement learning |
| CN109086492B (en) * | 2018-07-11 | 2022-12-13 | 大连理工大学 | Wire frame representation and deformation method and system for three-dimensional model of vehicle body structure |
| CN109086492A (en) * | 2018-07-11 | 2018-12-25 | 大连理工大学 | A kind of wire frame representation of body structure threedimensional model and deformation method and system |
| CN109188912A (en) * | 2018-10-12 | 2019-01-11 | 国网浙江省电力有限公司绍兴供电公司 | A kind of control method for energy storage device in grid-connected distributed energy resource system |
| CN109921924B (en) * | 2019-02-14 | 2021-07-13 | 电子科技大学 | Modeling method for intelligent automobile multilayer three-dimensional network connection control system |
| CN109921924A (en) * | 2019-02-14 | 2019-06-21 | 电子科技大学 | A kind of intelligent automobile multilayer stereoscopic joint control system modeling method |
| CN110310500A (en) * | 2019-06-19 | 2019-10-08 | 中汽研（天津）汽车工程研究院有限公司 | A kind of autonomous valet parking system and method based on GRNN network |
| US20220204018A1 (en) * | 2020-12-29 | 2022-06-30 | GM Global Technology Operations LLC | Vehicle control using neural network controller in combination with model-based controller |
| US11834066B2 (en) * | 2020-12-29 | 2023-12-05 | GM Global Technology Operations LLC | Vehicle control using neural network controller in combination with model-based controller |
| CN114701875A (en) * | 2022-03-08 | 2022-07-05 | 中国人民解放军空军工程大学 | Guiding device and method for loading and unloading of railway vehicle under light condition |
| CN116461499A (en) * | 2023-03-02 | 2023-07-21 | 合众新能源汽车股份有限公司 | Parking control method and device |
| CN116461499B (en) * | 2023-03-02 | 2024-01-02 | 合众新能源汽车股份有限公司 | Parking control method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107065567A (en) | A kind of automatic stopping control system that control is constrained based on adaptive neural network | |
| Hu et al. | Lane keeping control of autonomous vehicles with prescribed performance considering the rollover prevention and input saturation | |
| Polack et al. | The kinematic bicycle model: A consistent model for planning feasible trajectories for autonomous vehicles? | |
| Ni et al. | Envelope control for four-wheel independently actuated autonomous ground vehicle through AFS/DYC integrated control | |
| CN110286681B (en) | Dynamic automatic driving track-changing planning method for curvature-variable curve | |
| Erlien et al. | Safe driving envelopes for shared control of ground vehicles | |
| Wnag et al. | Path planning and stability control of collision avoidance system based on active front steering | |
| CN107697065B (en) | Automatic parking control method for general parking scene | |
| Zhao et al. | Emergency steering evasion assistance control based on driving behavior analysis | |
| Lee | A preview steering autopilot control algorithm for four-wheel-steering passenger vehicles | |
| Attia et al. | Coupled longitudinal and lateral control strategy improving lateral stability for autonomous vehicle | |
| CN111791898B (en) | Automatic driving automobile collision avoidance control method based on cooperation type game | |
| CN107380162B (en) | Collision avoidance method is cooperateed with based on function distribution and Multi-Objective Fuzzy Decision | |
| Yuan et al. | Mixed local motion planning and tracking control framework for autonomous vehicles based on model predictive control | |
| CN110161854A (en) | A kind of highway heavy truck formation longitudinal driving control method | |
| Ali et al. | Urban platooning using a flatbed tow truck model | |
| Fergani et al. | Full vehicle dynamics control based on LPV/ℋ∞ and flatness approaches | |
| Zhai et al. | Bilateral control of vehicle Steer-by-Wire system with variable gear-ratio | |
| CN107878453A (en) | A kind of automobile emergency collision avoidance integral type control method for hiding dynamic barrier | |
| CN107856733A (en) | It is a kind of to hide dynamic barrier control method towards man-machine harmonious automobile | |
| Zhang et al. | Minimum time lane changing problem of vehicle handling inverse dynamics considering the driver’s intention | |
| Chen et al. | Ribbon model based path tracking method for autonomous ground vehicles | |
| Teng et al. | Car following model based on driving risk field for vehicle infrastructure cooperation | |
| CN107963120A (en) | A kind of rubber tire low-floor intelligent track train automatic steering control method | |
| Tagne et al. | Passivity analysis and design of passivity-based controllers for trajectory tracking at high speed of autonomous vehicles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170818 |
|
| RJ01 | Rejection of invention patent application after publication |